Dispatch independent subagents to review code and merge severity-rated findings.
npx skills add https://github.com/cjohnhanson/almanac --skill full-review-cjohnhanson
Please help me install this Agent Skill. Skill: full-review Source: https://github.com/cjohnhanson/almanac/tree/main/skills/full-review Command: npx skills add https://github.com/cjohnhanson/almanac --skill full-review-cjohnhanson
Manages a parallel code review process, leveraging multiple review skills to provide a thorough and detailed evaluation of code changes.
Run /full-review for a comprehensive review of your code changes.
High-intent search queries and answers about installing and using this skill.
Run a comprehensive code review by dispatching multiple independent subagents in parallel, each performing a specific review task without shared context. This approach evaluates large codebases thoroughly by merging all findings into a single severity-ranked list with file:line locations and suggested fixes.
Severity ratings for code review findings are generated by independent subagents that evaluate code changes and report issues. Each subagent assigns a severity rating, includes file:line locations, and provides suggested fixes, which are then merged into a single severity-ranked list.
Yes, parallel subagents can review code changes without shared context. Each subagent operates independently on the same codebase, performing its specific review task and reporting findings without relying on the context of other subagents, ensuring an unbiased comprehensive evaluation.
Yes, you need multiple review skills to perform an end-to-end code review using this approach. The system leverages these skills as independent subagents to provide a thorough and detailed evaluation of code changes across large codebases.
Parallel processing improves code evaluation for large codebases by dispatching multiple independent subagents simultaneously. Each subagent handles a specific review task, reducing overall review time while providing a thorough evaluation merged into a severity-ranked list of findings.
yairbedermanDispatch independent subagents to execute plan tasks with fresh context.
jaisonerickReproduce QA-reported failures with failing tests and apply minimal code fixes.
julianobarbosaReview code for quality, bugs, security issues, and best practices using Codex.
CaptainCrouton89Evaluate code changes for security, correctness, performance, and spec alignment.
